bin/maintenance/fix_utf8_errors.py

   1 # This file is part of Indico.
   2 # Copyright (C) 2002 - 2015 European Organization for Nuclear Research (CERN).
   3 #
   4 # Indico is free software; you can redistribute it and/or
   5 # modify it under the terms of the GNU General Public License as
   6 # published by the Free Software Foundation; either version 3 of the
   7 # License, or (at your option) any later version.
   8 #
   9 # Indico is distributed in the hope that it will be useful, but
  10 # WITHOUT ANY WARRANTY; without even the implied warranty of
  11 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  12 # General Public License for more details.
  13 #
  14 # You should have received a copy of the GNU General Public License
  15 # along with Indico; if not, see <http://www.gnu.org/licenses/>.
  16
  17 """
  18 Fixes possible encoding errors caused by older DB data
  19 """
  20
  21 from indico.core.db import DBMgr
  22 from MaKaC.conference import ConferenceHolder
  23 from indico.util.console import conferenceHolderIterator
  24
  25
  26 def fix_prop(c, name):
  27     getter = getattr(c, 'get' + name)
  28     try:
  29         getter().decode('utf-8')
  30     except UnicodeDecodeError:
  31         print c.getId(), name
  32         getattr(c, 'set' + name)(getter().decode('latin1').encode('utf-8'))
  33
  34
  35 def fix_everything(dbi):
  36     i = 0
  37     for level, c in conferenceHolderIterator(ConferenceHolder(), deepness='event'):
  38         fix_prop(c, 'Title')
  39         fix_prop(c, 'Description')
  40
  41         for spk in c.getChairList():
  42             fix_prop(spk, 'Affiliation')
  43             fix_prop(spk, 'FamilyName')
  44             fix_prop(spk, 'FirstName')
  45
  46     if i % 999 == 0:
  47         dbi.commit()
  48     i += 1
  49
  50
  51 if __name__ == '__main__':
  52     dbi = DBMgr.getInstance()
  53     dbi.startRequest()
  54
  55     fix_everything(dbi)
  56
  57     dbi.endRequest()